从多个列表中随机创建“n”个组合

Question

def models():
    default = [0.6,0.67,2.4e-2,1e-2,2e-5,1.2e-3,2e-5]
    lower = [np.log10(i/10) for i in default]
    upper = [np.log10(i*10) for i in default]
    n = 5
    a = np.logspace(lower[0],upper[0],n)
    b = np.logspace(lower[1],upper[1],n)
    c = np.logspace(lower[2],upper[2],n)
    d = np.logspace(lower[3],upper[3],n)
    e = np.logspace(lower[4],upper[4],n)
    f = np.logspace(lower[5],upper[5],n)
    g = np.logspace(lower[6],upper[6],n)

    combs = itertools.product(a,b,c,d,e,f,g)

    list1 = []

    for x in combs:
        x = list(x)
        list1.append(x)


    return list1

The code above returns a list of 5^7 = 78,125 lists. Is there a way I can combine items in a,b,c,d,e,f,g, possibly randomly, to create a list of say, 10000, lists?

Answer 1

You could take random samples of each array and combine them, especially if you don't need to guarantee that specific combinations don't occur more than once:

import numpy as np
import random


def random_models(num_values):
    n = 5
    default = [0.6, 0.67, 2.4e-2, 1e-2, 2e-5, 1.2e-3, 2e-5]
    ranges = zip((np.log10(i/10) for i in default),
                 (np.log10(i*10) for i in default))

    data_arrays = []
    for lower, upper in ranges:
        data_arrays.append(np.logspace(lower, upper, n))

    results = []

    for i in xrange(num_values):
        results.append([random.choice(arr) for arr in data_arrays])

    return results


l = random_models(10000)
print len(l)

Here's a version that will avoid repeats up until you request more data than can be given without repeating:

def random_models_avoid_repeats(num_values):
    n = 5
    default = [0.6, 0.67, 2.4e-2, 1e-2, 2e-5, 1.2e-3, 2e-5]

    # Build the range data (tuples of (lower, upper) range)
    ranges = zip((np.log10(i/10) for i in default),
                 (np.log10(i*10) for i in default))

    # Create the data arrays to sample from
    data_arrays = []
    for lower, upper in ranges:
        data_arrays.append(np.logspace(lower, upper, n))

    sequence_data = []
    for entry in itertools.product(*data_arrays):
        sequence_data.append(entry)

    results = []

    # Holds the current choices to choose from.  The data will come from
    # sequence_data above, but randomly shuffled.  Values are popped off the
    # end to keep things efficient.  It's possible to ask for more data than
    # the samples can give without repeats.  In that case, we'll reload
    # temp_data, randomly shuffle again, and start the process over until we've
    # delivered the number of desired results.
    temp_data = []
    # Build the lists
    for i in xrange(num_values):
        if len(temp_data) == 0:
            temp_data = sequence_data[:]
            random.shuffle(temp_data)
        results.append(temp_data.pop())

    return results

Also note that we can avoid building a results list if you make this a generator by using yield . However, you'd want to consume the results using a for statement as well:

def random_models_avoid_repeats_generator(num_values):
    n = 5
    default = [0.6, 0.67, 2.4e-2, 1e-2, 2e-5, 1.2e-3, 2e-5]

    # Build the range data (tuples of (lower, upper) range)
    ranges = zip((np.log10(i/10) for i in default),
                 (np.log10(i*10) for i in default))

    # Create the data arrays to sample from
    data_arrays = []
    for lower, upper in ranges:
        data_arrays.append(np.logspace(lower, upper, n))

    sequence_data = []
    for entry in itertools.product(*data_arrays):
        sequence_data.append(entry)

    # Holds the current choices to choose from.  The data will come from
    # sequence_data above, but randomly shuffled.  Values are popped off the
    # end to keep things efficient.  It's possible to ask for more data than
    # the samples can give without repeats.  In that case, we'll reload
    # temp_data, randomly shuffle again, and start the process over until we've
    # delivered the number of desired results.
    temp_data = []
    # Build the lists
    for i in xrange(num_values):
        if len(temp_data) == 0:
            temp_data = sequence_data[:]
            random.shuffle(temp_data)
        yield temp_data.pop()

You'd have to use it like this:

for entry in random_models_avoid_repeats_generator(10000):
    # Do stuff...

Or manually iterate over it using next() .